English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Distant metastases (DM) refer to the dissemination of tumors, usually, beyondthe organ where the tumor originated. They are the leading cause of death inpatients with soft-tissue sarcomas (STSs). Positron emissiontomography-computed tomography (PET-CT) is regarded as the imaging modality ofchoice for the management of STSs. It is difficult to determine from imagingstudies which STS patients will develop metastases. 'Radiomics' refers to theextraction and analysis of quantitative features from medical images and it hasbeen employed to help identify such tumors. The state-of-the-art in radiomicsis based on convolutional neural networks (CNNs). Most CNNs are designed forsingle-modality imaging data (CT or PET alone) and do not exploit theinformation embedded in PET-CT where there is a combination of an anatomicaland functional imaging modality. Furthermore, most radiomic methods rely onmanual input from imaging specialists for tumor delineation, definition andselection of radiomic features. This approach, however, may not be scalable totumors with complex boundaries and where there are multiple other sites ofdisease. We outline a new 3D CNN to help predict DM in STS patients from PET-CTdata. The 3D CNN uses a constrained feature learning module and a hierarchicalmulti-modality feature learning module that leverages the complementaryinformation from the modalities to focus on semantically important regions. Ourresults on a public PET-CT dataset of STS patients show that multi-modalinformation improves the ability to identify those patients who develop DM.Further our method outperformed all other related state-of-the-art methods.

Predicting Distant Metastases in Soft-Tissue Sarcomas from PET-CT scans using Constrained Hierarchical Multi-Modality Feature Learning